© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33869
    Prev
    Next
    INDEX
    Explanations

    related compound C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥ī
    -0.09
    ioni
    -0.09
     sortOrder
    -0.09
    fung
    -0.09
    peria
    -0.08
    ASA
    -0.08
    kaar
    -0.08
    ä¹
    -0.08
     laz
    -0.08
     phosphate
    -0.08
    POSITIVE LOGITS
     products
    0.27
     side
    0.22
     Products
    0.21
    products
    0.20
     product
    0.18
    Products
    0.18
    -products
    0.18
     PRODUCTS
    0.17
    _products
    0.17
     secondary
    0.15
    Activations Density 0.032%

    No Known Activations